Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate universality or all-encompassing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.17
    iteit
    -0.16
     Daly
    -0.16
     Misc
    -0.15
    inn
    -0.15
     Murdoch
    -0.15
     Birch
    -0.15
     gravity
    -0.15
    apia
    -0.14
    alc
    -0.14
    POSITIVE LOGITS
     ÙĪÙĤت
    0.18
     æŶ
    0.17
     вÑĢемени
    0.17
     lúc
    0.17
     times
    0.16
    à¹Ģส
    0.16
    кÑĤа
    0.16
    æŶåĢĻ
    0.16
    wick
    0.16
     thá»Ŀi
    0.16
    Act Density 0.029%

    No Known Activations